Soccer Refereeing Explanation Quality on SoccerRefBench Video 1.0 (test)
2.76Referee 1 ScoreSoccerRef-Agents
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| SoccerRef-AgentsEvaluation Protocol=Human Evaluation2026.04 | 2.76 | 3.24 | 3.18 | 3.06 | |
| GPT-4oEvaluation Protocol=Human Evaluation2026.04 | 2.7 | 2.7 | 2.8 | 2.73 |